skills

Skills For Real Engineers

Website · GitHub · X

Forked from and built on Matt Pocock's skills. Matt is the original author; see Credits.

My agent skills for real engineering, not vibe coding: a curated library plus my own personal skills, linked into every project on my machine.

Developing real applications is hard. Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away your control and make bugs in the process hard to resolve.

These skills are designed to be small, easy to adapt, and composable. They work with any model. Hack around with them. Make them your own.

Quickstart

Clone the repo and run the reconcile linker. It mirrors every shippable skill into ~/.codex/skills, ~/.claude/skills, and ~/.agents/skills, installs helper scripts into ~/.local/bin, and registers git hooks so the link layer re-syncs itself on every pull.

git clone https://github.com/thatssoheil/skills.git
cd skills
bash scripts/link-skills.sh          # link skills + install bin/ + register hooks
bash scripts/link-skills.sh --check  # verify the mirror is in sync

personal/ and useful vendored third-party skills are linked globally; deprecated/ and in-progress/ are skipped. Editing a skill's body is live immediately; adding, renaming, or removing one re-syncs automatically via the hooks (or just re-run the script).

Cross-Agent Manifests

The source of truth is the Agent Skills directory layout: every skill is a folder with SKILL.md. Product-specific manifests sit beside it:

• .claude-plugin/plugin.json — public promoted set for Claude-style plugin installs.
• scripts/link-skills.sh — the local machine delivery path; this is what makes the repo global across Codex, Claude, and other Agent Skills clients.

Prefer the skills.sh installer? npx skills@latest add thatssoheil/skills pulls the public set declared in .claude-plugin/plugin.json (the public skill library) but not my personal/ skills. The clone + reconcile path above is how I actually use it.

Why These Skills Exist

The philosophy below is Matt Pocock's, in his own words. It is why these skills exist, and why I forked them. I've adapted and extended the set for my own workflow; the thinking is his.

Matt built these skills as a way to fix common failure modes he saw with Claude Code, Codex, and other coding agents.

#1: The Agent Didn't Do What I Want

"No-one knows exactly what they want"

David Thomas & Andrew Hunt, The Pragmatic Programmer

The Problem. The most common failure mode in software development is misalignment. You think the dev knows what you want. Then you see what they've built - and you realize it didn't understand you at all.

This is just the same in the AI age. There is a communication gap between you and the agent. The fix for this is a grilling session - getting the agent to ask you detailed questions about what you're building.

The Fix is to use:

• /grill-me - for non-code uses
• /grill-with-docs - same as /grill-me, but adds more goodies (see below)

These are my most popular skills. They help you align with the agent before you get started, and think deeply about the change you're making. Use them every time you want to make a change.

#2: The Agent Is Way Too Verbose

With a ubiquitous language, conversations among developers and expressions of the code are all derived from the same domain model.

Eric Evans, Domain-Driven-Design

The Problem: At the start of a project, devs and the people they're building the software for (the domain experts) are usually speaking different languages.

I felt the same tension with my agents. Agents are usually dropped into a project and asked to figure out the jargon as they go. So they use 20 words where 1 will do.

The Fix for this is a shared language. It's a document that helps agents decode the jargon used in the project.

Example

Here's an example CONTEXT.md, from my course-video-manager repo. Which one is easier to read?

• BEFORE: "There's a problem when a lesson inside a section of a course is made 'real' (i.e. given a spot in the file system)"
• AFTER: "There's a problem with the materialization cascade"

This concision pays off session after session.